Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add fortunto2/solo-factory --skill setupgit clone --depth 1 https://github.com/fortunto2/solo-factoryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fortunto2/solo-factory/setup)<a href="https://agentmods.dev/skills/fortunto2/solo-factory/setup"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fortunto2/solo-factory/setup"><img src="https://agentmods.dev/badge/skills/fortunto2/solo-factory/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01259 |
| Opus 5.5 | $0.00020 | $0.00504 |
| Sonnet 5.5 | $0.00010 | $0.00252 |
| Haiku 4.5 | $0.00005 | $0.00126 |
Grade A, and why
solo-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/setup
Auto-generate project workflow config from existing PRD and CLAUDE.md. Zero interactive questions — all answers extracted from project data that already exists after /scaffold.
When to use
After /scaffold creates a project, before /plan. Creates docs/workflow.md so /plan and /build can work.
MCP Tools (use if available)
project_info(name)— get project details, detected stackkb_search(query)— search for dev principles, manifest, stack templatesproject_info(name)— project stack and dependencies
If MCP tools are not available, fall back to reading local files only.
Steps
-
Detect project root:
- If
$ARGUMENTSis provided, look for a project with that name in the current directory orprojects_dirfrom~/.solo-factory/defaults.yaml. - Otherwise use current working directory.
- Verify the directory exists and has
CLAUDE.md. - If not found, ask via AskUserQuestion.
- If
-
Check if already initialized:
- If
docs/workflow.mdexists, warn and ask whether to regenerate.
- If
-
Read project data (parallel — all reads at once):
CLAUDE.md— tech stack, architecture, commands, Do/Don'tdocs/prd.md— problem, users, solution, features, metrics, pricingpackage.jsonorpyproject.toml— exact dependency versionsMakefile— available commands- Linter configs (
.eslintrc*,eslint.config.*,.swiftlint.yml,ruff.toml,detekt.yml)
-
Read ecosystem sources (optional — enhances quality):
- Detect stack name from CLAUDE.md (look for "Stack:" or the stack name in tech section).
- If MCP
kb_searchavailable: search for stack template and dev-principles. - Otherwise: look for
stacks/<stack>.yamlanddev-principles.md+dev-principles-my.md(personal extensions) in.solo/or plugin templates directory (if accessible). - If neither available: derive all info from CLAUDE.md + package manifest (sufficient).
-
Detect languages from package manifest:
package.json→ TypeScriptpyproject.toml→ Python*.xcodeprojorPackage.swift→ Swiftbuild.gradle.kts→ Kotlin
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed c0891ed2c8f4
- 2d ago Changed · +5 lines b213ddd2086f
- 2mo ago First seen · 123 lines · 51 tokens per session scan A cd6d4779f4eb
solo-setup is a skill published in the GitHub repository fortunto2/solo-factory (19 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,259 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
building
Use when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
hk-rca
Interactive Root Cause Analysis enforcer. Guides you through the 7-step RCA protocol: Reproduce, Locate, Hypothesis, Failing Test, Fix, Verify Live, Document. Use when debugging a bug, investigating a failure, or when something unexpected happened. This skill gates each step — it won't let you skip to a fix without…
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
tdd
A test-driven development guide. TDD means writing a failing test for a public behavior, making it pass with the smallest change, and then repeating the cycle.
test-driven-development
Forces the strict Red-Green-Refactor development cycle. Requires one failing behavior test through a public interface before each implementation slice.